Commit graph

9 commits

Author SHA1 Message Date
Armin Ronacher
b6d505cd1f fix(codemode): reject // @options: lines that are not the first line
A misplaced options line was ignored, so its timeout_ms never applied and
the script ran without a deadline. parseCodemodeSource now throws
CodemodeSourceError before the script runs.

fixes #10631
2026-10-12 17:55:33 +02:00
Armin Ronacher
24382bedd0 refactor(codemode,coding-agent): decouple MCP from codemode
Tools that reach other tools declare it with reachesTools(input); MCP uses it to wait for the servers a call needs and to decide which codemode or tool_search tool to activate, instead of parsing codemode scripts and comparing parameter schemas. Namespaces get aliases, replacing codemode's MCP-specific __ suffix rule.

pi-codemode no longer knows MCP: MCP_TYPESCRIPT_PREAMBLE and mcpStructuredContentSchema() are removed, and the MCP result schema describes itself, with the server's local $refs relocated so they resolve as before.
2026-10-12 09:19:30 +02:00
Armin Ronacher
8a9c051f80 feat(codemode): show schema constraints in tool declarations
Property comments now carry constraints the TypeScript type cannot
express (integer, bounds, lengths, pattern, format, default, ...) as
@ tags, read from nullable anyOf branches too. Types over the size
limit are rendered again without tags before becoming unknown.

closes #10707
2026-10-11 22:19:06 +02:00
Mario Zechner
0fb1aee749 feat(codemode): deterministic runs that the host answers (sandbox.start)
For durable code mode: a host can rerun a script after a restart and get the
same calls with the same arguments. start() runs the script with a virtual
clock (startedAt, then each result's time, never backwards), randomness from a
seed, UTC, no WeakRef/FinalizationRegistry, and the run's own tools and
globals; every call goes to onCall with the VM's call id, and the host answers
with run.deliver(seq, now, id, outcome). The VM applies results strictly in
seq order whatever the transport does, reports its fingerprint (engine
versions, prelude hash, limits) before the script runs, the calls issued after
each result (onIdle), and the result it was processing when the script ended
(result.during). Rejections can carry properties for the script's Error.
execute() is unchanged.
2026-10-11 19:50:26 +00:00
Armin Ronacher
748b351fe2 feat(codemode): run sandboxes on Cloudflare Workers via a remote Durable Object
Split the host into transport-independent execution logic and a VM driver, so the VM can run in a worker thread (CodemodeSandbox, unchanged), on the calling thread (InlineCodemodeSandbox), or in another isolate over RPC (RemoteCodemodeSandbox).

Add the /portable entry without Node imports and the /cloudflare entry with CodemodeSandboxDurableObject, meant to be deployed as its own Worker so scripts never block the caller's thread. Scripts that compute without awaiting a tool are bounded by an interrupt budget, now also polled while draining promise jobs. examples/cloudflare shows the setup.
2026-10-10 14:41:36 +02:00
Armin Ronacher
eb326d265a fix(codemode,coding-agent): separate codemode output items
Text items get ==> text N/M <== headers when there are several, and
console output is grouped into one <console_output> block. Console text
items are marked with console: true.
2026-10-06 23:51:09 +02:00
Armin Ronacher
319fecb89b fix(codemode): cap script output so print loops cannot exhaust host memory
text(), image(), and console.* fail the script with a RangeError past
MAX_OUTPUT_CHARS (16 Mi) characters or MAX_OUTPUT_ITEMS (100000) items.

closes #10283
2026-10-02 17:54:35 +02:00
Armin Ronacher
4a42f8fafa fix(coding-agent): load codemode worker in Windows binary
closes #10204
2026-09-30 13:48:04 +02:00
Armin Ronacher
8562bcf66a feat(coding-agent): codemode and MCP
This adds codemode and MCP support to pi. Codemode (packages/codemode) runs
model-written JavaScript in a QuickJS wasm VM inside a worker. From there the
script calls pi's tools as async functions, uses a per-session store, and can
read the model catalog and run classifiers. The codemode tool in coding-agent
is compatible with Codex's exec tool, and codemode.mode works like Codex's
tool modes (on or only). Large results are written to a JSON temp file. MCP
(packages/mcp) is a standalone client for stdio and streamable HTTP servers,
with OAuth.

The core only gets general mechanisms; codemode, tool_search and MCP are
built-in extensions that use them. Other extensions can replace these
built-ins. Tools declare an exposure: direct, model-only, codemode, deferred
or hidden. prepareLoadout() lets an orchestrating tool change which tool
declarations the model sees. ctx.executeTool() runs nested calls through
validation and the tool_call/tool_result hooks. Those calls emit events with
parentToolCallId and are recorded as bounded nestedCalls on the parent
result, which compaction and HTML export use. Tools can also return
structuredContent with an outputSchema, and can report errors with isError
instead of throwing. MCP servers come from mcp.json (global, or per project
after the project is trusted) or from pi.registerMcpServer(). They are
managed with /mcp and pi mcp list|login|logout, and their runtimes load on
first use.

Closes #10040
2026-09-29 09:12:50 +02:00